CN109192207A - Voice communication assembly, voice communication method and system, equipment, storage medium - Google Patents
Voice communication assembly, voice communication method and system, equipment, storage medium Download PDFInfo
- Publication number
- CN109192207A CN109192207A CN201811081767.6A CN201811081767A CN109192207A CN 109192207 A CN109192207 A CN 109192207A CN 201811081767 A CN201811081767 A CN 201811081767A CN 109192207 A CN109192207 A CN 109192207A
- Authority
- CN
- China
- Prior art keywords
- target information
- voice communication
- server
- audio data
- voice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004891 communication Methods 0.000 title claims abstract description 106
- 238000000034 method Methods 0.000 title claims abstract description 28
- 239000000284 extract Substances 0.000 claims description 40
- 238000000605 extraction Methods 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 206010039203 Road traffic accident Diseases 0.000 abstract description 4
- 230000003014 reinforcing effect Effects 0.000 abstract description 2
- 230000006978 adaptation Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000005266 casting Methods 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B5/00—Near-field transmission systems, e.g. inductive loop type
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention relates to a kind of voice communication assembly, voice communication method and system, equipment, storage medium, the voice communication method, comprising: receive the first voice signal；It is extracted based on the first voice signal and identifies target information；Search and the matched called side of target information；Voice communication request is sent to called side.Improve the fast efficiency received and send part；User experience when courier's receipts send part under special screne is promoted, while reinforcing safety precaution when riding, reduces traffic accident incidence.
Description
Technical field
The present invention relates to express mail and logistics field more particularly to a kind of voice communication assembly, voice communication method and system,
Equipment, storage medium.
Background technique
With e-commerce and the high speed development of O2O, logistics also flourishes therewith as a wherein important ring, is
It improving efficiency, major express company gives small brother to be equipped with the terminal of electronization one after another in order to improve and pull receipts and send part efficiency, such as
Robbed along rich bar, bar rob in configured with SIM card, dial customer phone by a bar rifle screen taps.
Although having used the terminal device of electronization, the both hands of courier could not be still liberated, courier pulls receipts express delivery
And send with charge free express delivery operation it is still comparatively laborious, for above school's part, courier needs to put down the express delivery in hand, takes out bar
Rifle opens related application, and scans express waybill, dials customer phone by a bar rifle screen taps, could breathe out client's
Phone is contacted.
Also, under some special screnes, courier was riding sometimes in order to be delivered to fastly in client's hand as early as possible
Order is carried out in journey, turns the operation such as single, connection client, these operations are required to carry out telephonic communication with other side, when making a phone call
Screen taps operation, extremely be easy to cause safety accident.
The method of the invention sends the application scenarios of terminal in conjunction with receipts based on the in-depth analysis to corporate business, innovative
Ground proposes the method that intelligent sound technology realizes voice communication, pulls receipts to improve the express delivery of courier and sends efficiency with charge free, arranges in pairs or groups simultaneously
Band can the smart bluetooth earphone that wakes up of voice, the small brother's both hands of thorough liberation ensure the safety of courier.
Summary of the invention
In order to solve the above-mentioned technical problem, the purpose of the present invention is to provide a kind of voice communication assemblies, voice communication side
Method and system, equipment, storage medium.
According to an aspect of the invention, there is provided a kind of voice communication method, comprising:
Receive the first voice signal；
It is extracted based on the first voice signal and identifies target information；
Search and the matched called side of target information；
Voice communication request is sent to called side.
Further, before the first voice signal of reception, further includes: trigger and mention after the AT instruction that reception bluetooth headset is sent
Show information.
Further, receiving the first voice signal includes: that recoding unit acquisition sound is called after detecting the first voice signal
Frequency evidence.
Further, target information is extracted based on the first voice signal, including, while target letter is extracted by multiple modes
Breath, and judge whether to recognize target information, if so, terminating the extraction to target information.
Further, described to extract target information simultaneously by multiple modes, include the following:
Mode 1: sending request and corresponding audio data to first server, and first server receives after request by the
The web api interface of two servers extracts the target information of audio data and return；
Mode 2: the sdk interface that audio data write-in second server is provided extracts sound by second server
The target information of frequency evidence is simultaneously returned to target information by the sdk interface；
Mode 3: calling local identification engine MSC, identifies the audio data by the local grammar file of pre-configuration, mentions
Take the target information of audio data.
Further, the extraction to target information is terminated, comprising:
It terminates and extracts the target information for having received the first voice signal and destroy recording thread；
It terminates to send request and corresponding audio data to first server and/or terminate to the SDK of second server and connect
Mouth write-in audio data and/or the target information extraction for terminating local identification engine MSC.
Further, extracting target character includes: the semantic slot for identifying target information, extracts target according to the semantic slot
Character.
Further, the target character includes telephone number and/or Air Way Bill No..
According to another aspect of the present invention, a kind of voice communication assembly is provided, comprising:
Communication unit is configured to receive the first voice signal；
Control unit is configured to be extracted based on the first voice signal and identified target information；
Search unit is configured to search and the matched called side of target information；
Voice communication units are configured to send voice communication request to called side.
Further, described search unit, voice communication units are configured in the APP of voice communication assembly；
And/or
Communication unit is also configured to, and receives AT instruction.
It further, further include detection unit,
The detection unit is configured to detect whether to have received the first voice signal, for detecting the first voice signal
Afterwards, control unit calls recoding unit to acquire audio data.
Further, target information is extracted based on the first voice signal, comprising: control unit is mentioned by multiple modes simultaneously
Target information is taken, and judges whether to recognize target information, if so, terminating the extraction to target information.
Further, described to extract target information simultaneously by multiple modes, include the following:
Mode 1: request and corresponding audio data are sent to first server by communication unit, server receives request
Target information and the return of audio data are extracted by the web api interface of second server afterwards, communication unit receives the first clothes
The target information that business device returns；
Mode 2: the sdk interface that audio data write-in second server is provided extracts sound by second server
The target information of frequency evidence is simultaneously returned to target information by the sdk interface, and communication unit receives the mesh that second server returns
Mark information；
Mode 3: calling local identification engine MSC, identifies the audio data by the local grammar file of pre-configuration, mentions
Take the target information of audio data.
Further, the extraction to target information is terminated, comprising:
It terminates and extracts the target information for having received the first voice signal and destroy recording thread；
Communication unit is terminated to send request and corresponding audio data to first server and/or terminate to second server
Sdk interface, which is written audio data and/or terminates local identification engine MSC, extracts target information.
Further, control unit is also configured to, and identifies the semantic slot of target information, extracts target word according to semantic slot
Symbol.
Further, the target character includes telephone number and/or Air Way Bill No..
According to another aspect of the present invention, a kind of voice communication system is provided, comprising: bluetooth headset and one above-mentioned
The voice communication assembly；
Bluetooth headset, for sending AT instruction to voice communication assembly after the second voice signal of reception；
Voice communication assembly triggers prompt information after receiving AT instruction.
Further, the bluetooth headset is configured with voice Rouser, and bluetooth headset receives preset second voice letter
It number can be waken up.
It further, further include first server, second server；
First server is configured to receive the request and corresponding audio data that voice communication assembly is sent, first service
Target information and the return of audio data are extracted after device reception request by the web api interface of second server；
Second server is configured to the audio data that sdk interface obtains voice communication assembly write-in, extracts audio
The target information of data is simultaneously returned to target information by the sdk interface.
According to another aspect of the present invention, a kind of equipment, including one or more processors are provided；
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of places
It manages device and executes as above described in any item methods.
According to another aspect of the present invention, a kind of computer-readable storage medium for being stored with computer program is provided
Matter realizes as above described in any item methods when the program is executed by processor.
Compared with prior art, the invention has the following advantages:
1, voice communication method of the present invention can liberate courier's both hands, improve the fast efficiency received and send part；Promote courier
User experience when sending part under special screne is received, while reinforcing safety precaution when riding, reduces traffic accident incidence.
2, voice communication assembly of the present invention directly can input phonetic order to voice communication assembly by user, directly
Voice communication request is sent to called side, liberates courier's both hands, improves the fast efficiency received and send part；It promotes courier's receipts and sends part
When user experience under special screne, while reducing both hands when riding and touching bar rifle screen, the both hands of courier do not have to from
It drives to reduce traffic accident incidence operation handlebar rifle screen is removed.
3, the exemplary voice communication system of the present invention, including bluetooth headset and voice communication assembly, not will increase courier
Weight bearing, can directly by user to voice communication assembly input phonetic order, directly to called side send voice communication
Request is answered after establishing communication by bluetooth headset, and courier's both hands are liberated, and improves the fast efficiency received and send part；Promote courier
User experience when sending part under special screne is received, while reducing both hands when riding and touching bar rifle screen, reduces traffic accident
Incidence.
4, the exemplary equipment of the present invention executes voice communication method by processor, can the small brother's both hands of thorough liberation, protect
Hinder the safety of courier.
5, the exemplary readable storage medium storing program for executing of the present invention, stores the voice communication side realized when being executed by processor
Method, using and promoting convenient for voice communication assembly.
Detailed description of the invention
Fig. 1 is flow chart of the present invention.
Fig. 2 is the structural block diagram of voice communication system of the present invention.
Specific embodiment
In order to be better understood by technical solution of the present invention, combined with specific embodiments below, Figure of description is to the present invention
It is described further.
Embodiment 1:
A kind of voice communication assembly is present embodiments provided, can be bar rifle.
The voice communication assembly includes:
Communication unit is configured to receive AT instruction, the first voice signal, request to first server transmission and corresponding
Audio data；Receive the target information that server returns；
Detection unit is configured to detect whether to have received the first voice signal, after detecting the first voice signal,
Control unit calls recoding unit to acquire audio data.
Control unit is configured to be extracted based on the first voice signal and identified target information；Identify the language of target information
Adopted slot extracts target character according to semantic slot.Semantic slot is the keyword extracted from user's saying, and such as corresponding grammer is " I
Look for Air Way Bill No. { waybill number } ", semantic slot is exactly waybill number, as user says " I will look for 6587 ", mesh
It is " 6587 " that marking-up, which accords with value,.
Search unit is configured to search and the matched called side of target character from the current list.
Voice communication units are configured to send voice communication request to called side, wherein described search unit, language
Sound communication unit is configured in the APP of voice communication assembly.The application voice communication assembly is bar rifle, and android is a bar rifle
System-based, system recording are a part of android, and the AudioRecorder object provided by HAL layers of Android is adopted
Collect audio data.
It is extracted based on the first voice signal and identifies target information, comprising: control unit is extracted by multiple modes simultaneously
Target information, and judge whether to recognize target information, if so, terminating the extraction to target information.Especially by following 3 kinds
Mode:
Mode 1: request and corresponding audio data are sent to first server by communication unit, server receives request
Target information and the return of audio data are extracted by the web api interface of second server afterwards, communication unit receives the first clothes
The target information that business device returns；
Mode 2: the sdk interface that audio data write-in second server is provided extracts sound by second server
The target information of frequency evidence is simultaneously returned to target information by the sdk interface, and communication unit receives the mesh that second server returns
Mark information；
The target information that communication unit receives first server, second server returns；
Mode 3: calling local identification engine MSC, identifies the audio data by the local grammar file of pre-configuration,
(after adapted processing) extracts the target information of audio data.Adaptation processing refers to the adaptation of data format, because of local grammer
The format and webapi format that file acquisition arrives are inconsistent, and webapi is json format, and data field is different, and to handle is one
It causes, applies app to obtain required information to facilitate.The result that local msc is got needs voluntarily to be assembled into specific json
Format.
Mode 1, mode 2, mode 3 can extract the target information of audio data simultaneously, and control unit is also configured to, judgement
Whether target information is recognized, if so, terminating the extraction to target information.It specifically includes: terminating extraction and received the first language
The target information of sound signal simultaneously destroys recording thread；It terminates communication unit and sends request and corresponding audio data to server
And/or it terminates that audio data is written to second server sdk interface and/or terminates local identification engine MSC and extracts target information.
Its corresponding voice communication method of the voice communication assembly, comprising the following steps:
S1: prompt information is triggered after receiving AT instruction, AT instruction is sent after receiving the second voice signal by bluetooth headset；
S2: the first voice signal is received；
S3: it is extracted based on the first voice signal and identifies target information；
Include: control unit while extracting target information by multiple modes, and judges whether to recognize target information, if
It is then to terminate the extraction to target information.Especially by following 3 kinds of modes:
Mode 1: sending request and corresponding audio data to first server, and first server receives after request by the
The web api interface of two servers extracts the target information of audio data and return；
Mode 2: the sdk interface that audio data write-in second server is provided extracts sound by second server
The target information of frequency evidence is simultaneously returned to target information by the sdk interface；
The target information that communication unit receives first server, second server returns；
Mode 3: calling local identification engine MSC, identifies the audio data by the local grammar file of pre-configuration,
(after adapted processing) extracts the target information of audio data.Adaptation processing refers to the adaptation of data format, because of local grammer
The format and webapi format that file acquisition arrives are inconsistent, and webapi is json format, and data field is different, and to handle is one
It causes, applies app to obtain required information to facilitate.The result that local msc is got needs voluntarily to be assembled into specific json
Format.
Mode 1, mode 2, mode 3 can extract the target information of audio data simultaneously, and control unit is also configured to, judgement
Whether target information is recognized, if so, terminating the extraction to target information.It specifically includes: terminating extraction and received the first language
The target information of sound signal simultaneously destroys recording thread；It terminates communication unit and sends request and corresponding audio data to server
And/or it terminates that audio data is written to second server sdk interface and/or terminates local identification engine MSC and extracts target information.
S4: identifying the semantic slot of target information, extracts target character according to semantic slot.
S5: search and the matched called side of target character from gun system list；
S6: voice communication request is sent to called side.
Present embodiments provide a kind of voice communication system include: bluetooth headset, first server, second server and on
State voice communication assembly described in any one；
Bluetooth headset is configured with voice Rouser, and bluetooth headset receives preset second voice signal and can wake up.
Bluetooth headset is waken up after receiving the second voice signal, sends AT instruction to voice communication assembly；Voice communication dress
It sets and triggers prompt information after receiving AT instruction, user is reminded to send the first voice signal to voice communication assembly.
First server is configured to receive the request and corresponding audio data that voice communication assembly is sent, first service
Target information and the return of audio data are extracted after device reception request by the web api interface of second server；
Second server is configured to the audio data that sdk interface obtains voice communication assembly write-in, extracts audio
The target information of data is simultaneously returned to target information by the sdk interface.
Following citings are illustrated the system:
For sending part scene to dial customer phone, specifically, the first step is called out using phonetic order (the second voice signal)
Awake bluetooth headset, steps are as follows:
S11: matching in bar gun system setting and connection bluetooth headset
S12: the blue-tooth device in bar rifle starts with bar gun system, and keeps running background.
S13: bluetooth headset is waken up by phonetic order (such as " evil spirit flies evil spirit and flies ").
S14: bluetooth headset sends AT instruction to bar rifle after being waken up.
Second step receives the first voice signal, and steps are as follows:
S21: after the blue-tooth device on bar rifle receives AT instruction, pass through casting one section of signal language " I please say " (triggering
Prompt information), to inform that bluetooth headset has woken up user at this time.
S22: user hears signal language, can directly say input voice (the first voice signal), such as: " making a phone call, xxxx ",
Wherein xxxx is that the user sends the four figures after sending part list tail number in part list, which can be direct on courier packages
See.
Third step is directly or invoking server extracts target information, and steps are as follows:
S31: the blue-tooth device in bar rifle opens the channel bluetooth SCO, after detecting the first voice signal, calls the language of bar rifle
Sound identifies API, acquires the audio data of PCM format.
S32: point three extraction routes extract target information:
S32-1: being detected by VAD, is obtained audio data, is sent to first server, first service using http protocol
After device receives request, the target information of audio data is extracted by the web api interface of second server, target information is returned
Back to a bar rifle.
S32-2: second server sdk interface is written into collected PCM audio data, sound is extracted by second server
The target information of frequency evidence and by the sdk interface by target information, target information is returned into a bar rifle.
S32-3: calling local identification engine MSC, identifies the audio data, warp by the local grammar file of pre-configuration
Audio data is converted into target information after adaptation processing, guarantees audio data can also be converted under weak net and without net environment
For target information.
The strategy of S33: three extraction routes are as follows:
Identification each time is believed using being most fastly converted to audio data subject to the route of target information once recognizing target
Breath then terminates remaining and extracts route,
4th step notifies corresponding APP to make logical action, and steps are as follows:
S41: the blue-tooth device in bar rifle extracts four figures waybill tail number by the semantic slot in target information, with
Json data format passes to APP
After S42:APP receives rear 4-digit number, four matched waybills of tail number after searching in part list are sent from active user.
S43: voice prompting being triggered after finding waybill: dialing the phone of waybill tail number xxxx, casting is completed, this is dialed
The corresponding telephone number of waybill.In addition, user can also send the voice for terminating call as bar rifle during voice prompting, realize
Barge interaction.
S44: after call is completed, the blue-tooth device in bar rifle closes the channel bluetooth SCO, and earphone enters standby mode, supervises
It listens and wakes up next time.
A kind of equipment is present embodiments provided, the equipment includes:
One or more processors；
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of places
It manages device and executes as above described in any item methods.
A kind of computer readable storage medium for being stored with computer program is present embodiments provided, the program is by processor
As above described in any item methods are realized when execution.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from the inventive concept, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Energy.
Claims (21)
1. a kind of voice communication method characterized by comprising
Receive the first voice signal；
It is extracted based on the first voice signal and identifies target information；
Search and the matched called side of target information；
Voice communication request is sent to called side.
2. voice communication method according to claim 1, which is characterized in that before the first voice signal of reception, further includes:
Prompt information is triggered after receiving the AT instruction that bluetooth headset is sent.
3. voice communication method according to claim 1, which is characterized in that receiving the first voice signal includes: to detect
Recoding unit is called to acquire audio data after first voice signal.
4. voice communication method according to claim 1, which is characterized in that extract target letter based on the first voice signal
Breath, including, while target information is extracted by multiple modes, and judge whether to recognize target information, if so, terminating to mesh
Mark the extraction of information.
5. voice communication method according to claim 4, which is characterized in that described to extract target simultaneously by multiple modes
Information includes the following:
Mode 1: request and corresponding audio data are sent to first server, first server passes through the second clothes after receiving request
The web api interface of business device extracts target information and the return of audio data；
Mode 2: the sdk interface that audio data write-in second server is provided extracts audio number by second server
According to target information and target information is returned by the sdk interface；
Mode 3: calling local identification engine MSC, identifies the audio data by the local grammar file of pre-configuration, extracts sound
The target information of frequency evidence.
6. voice communication method according to claim 4, which is characterized in that
Terminate the extraction to target information, comprising:
It terminates and extracts the target information for having received the first voice signal and destroy recording thread；
It terminates to send request and corresponding audio data to server and/or terminate server S DK audio stream and audio data is written
And/or terminate the target information extraction of local identification engine MSC.
7. voice communication method according to claim 1, which is characterized in that extracting target character includes: identification target letter
The semantic slot of breath extracts target character according to the semantic slot.
8. voice communication method described in -7 according to claim 1, which is characterized in that the target character includes telephone number
And/or Air Way Bill No..
9. a kind of voice communication assembly characterized by comprising
Communication unit is configured to receive the first voice signal；
Control unit is configured to be extracted based on the first voice signal and identified target information；
Search unit is configured to search and the matched called side of target information；
Voice communication units are configured to send voice communication request to called side.
10. voice communication assembly according to claim 9, which is characterized in that described search unit, voice communication units are matched
It is placed in the APP of voice communication assembly；
And/or
Communication unit is also configured to, and receives AT instruction.
11. voice communication assembly according to claim 9, which is characterized in that it further include detection unit,
The detection unit is configured to detect whether to have received the first voice signal, after detecting the first voice signal,
Control unit calls recoding unit to acquire audio data.
12. voice communication assembly according to claim 9, which is characterized in that extract target letter based on the first voice signal
Breath, comprising: control unit extracts target information by multiple modes simultaneously, and judges whether to recognize target information, if so,
Terminate the extraction to target information.
13. voice communication assembly according to claim 12, which is characterized in that
It is described to extract target information simultaneously by multiple modes, include the following:
Mode 1: request and corresponding audio data are sent to first server by communication unit, server leads to after receiving request
The web api interface for crossing second server extracts target information and the return of audio data, and communication unit receives first server
The target information of return；
Mode 2: the sdk interface that audio data write-in second server is provided extracts audio number by second server
According to target information and target information is returned by the sdk interface, communication unit receive second server return target letter
Breath；
Mode 3: calling local identification engine MSC, identifies the audio data by the local grammar file of pre-configuration, extracts sound
The target information of frequency evidence.
14. voice communication assembly according to claim 12, which is characterized in that
Terminate the extraction to target information, comprising:
It terminates and extracts the target information for having received the first voice signal and destroy recording thread；
Communication unit is terminated to send request and corresponding audio data to server and/or terminate to second server sdk interface
Audio data is written and/or terminates local identification engine MSC and extracts target information.
15. voice communication assembly according to claim 9, which is characterized in that control unit is also configured to, and identifies target
The semantic slot of information extracts target character according to semantic slot.
16. according to voice communication assembly described in claim 9-15, which is characterized in that the target character includes telephone number
And/or Air Way Bill No..
17. a kind of voice communication system characterized by comprising described in bluetooth headset and claim 9-16 any one
Voice communication assembly；
Bluetooth headset, for sending AT instruction to voice communication assembly after the second voice signal of reception；
Voice communication assembly triggers prompt information after receiving AT instruction.
18. voice communication system according to claim 17, which is characterized in that the bluetooth headset wakes up configured with voice
Device, bluetooth headset receive preset second voice signal and can be waken up.
19. voice communication system according to claim 17, which is characterized in that further include first server, second service
Device；
First server is configured to the request for receiving voice communication assembly transmission and corresponding audio data, first server connect
Receive target information and the return for extracting audio data after requesting by the web api interface of second server；
Second server is configured to the audio data that sdk interface obtains voice communication assembly write-in, extracts audio data
Target information and target information is returned by the sdk interface.
20. a kind of equipment, which is characterized in that the equipment includes:
One or more processors；
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors
Execute such as method of any of claims 1-8.
21. a kind of computer readable storage medium for being stored with computer program, which is characterized in that the program is executed by processor
Shi Shixian method for example of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811081767.6A CN109192207A (en) | 2018-09-17 | 2018-09-17 | Voice communication assembly, voice communication method and system, equipment, storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811081767.6A CN109192207A (en) | 2018-09-17 | 2018-09-17 | Voice communication assembly, voice communication method and system, equipment, storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109192207A true CN109192207A (en) | 2019-01-11 |
Family
ID=64911587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811081767.6A Pending CN109192207A (en) | 2018-09-17 | 2018-09-17 | Voice communication assembly, voice communication method and system, equipment, storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109192207A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111131632A (en) * | 2019-12-24 | 2020-05-08 | 贵阳朗玛信息技术股份有限公司 | Method and system for distributing express |
| CN111756935A (en) * | 2019-12-12 | 2020-10-09 | 北京沃东天骏信息技术有限公司 | Information processing method of intelligent system and intelligent system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1764945A (en) * | 2003-03-25 | 2006-04-26 | 法国电信 | Distributed speech recognition system |
| US20130102295A1 (en) * | 2011-10-21 | 2013-04-25 | GM Global Technology Operations LLC | Mobile voice platform architecture with remote service interfaces |
| CN103501382A (en) * | 2013-09-17 | 2014-01-08 | 小米科技有限责任公司 | Voice service providing method, device and terminal |
| CN103559290A (en) * | 2013-11-08 | 2014-02-05 | 安徽科大讯飞信息科技股份有限公司 | Method and system for searching POI (point of interest) |
| WO2014069120A1 (en) * | 2012-10-31 | 2014-05-08 | 日本電気株式会社 | Analysis object determination device and analysis object determination method |
| CN104079711A (en) * | 2013-03-29 | 2014-10-01 | 上海城际互通通信有限公司 | Calling method based on speech recognition |
| CN204316540U (en) * | 2014-11-15 | 2015-05-06 | 深圳市掌翼星通科技有限公司 | A kind of vehicle-carried sound-controlled voice Telephoning system |
| CN107895578A (en) * | 2017-11-15 | 2018-04-10 | 百度在线网络技术（北京）有限公司 | Voice interactive method and device |
| CN107978316A (en) * | 2017-11-15 | 2018-05-01 | 西安蜂语信息科技有限公司 | The method and device of control terminal |
-
2018
- 2018-09-17 CN CN201811081767.6A patent/CN109192207A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1764945A (en) * | 2003-03-25 | 2006-04-26 | 法国电信 | Distributed speech recognition system |
| US20130102295A1 (en) * | 2011-10-21 | 2013-04-25 | GM Global Technology Operations LLC | Mobile voice platform architecture with remote service interfaces |
| WO2014069120A1 (en) * | 2012-10-31 | 2014-05-08 | 日本電気株式会社 | Analysis object determination device and analysis object determination method |
| CN104079711A (en) * | 2013-03-29 | 2014-10-01 | 上海城际互通通信有限公司 | Calling method based on speech recognition |
| CN103501382A (en) * | 2013-09-17 | 2014-01-08 | 小米科技有限责任公司 | Voice service providing method, device and terminal |
| CN103559290A (en) * | 2013-11-08 | 2014-02-05 | 安徽科大讯飞信息科技股份有限公司 | Method and system for searching POI (point of interest) |
| CN204316540U (en) * | 2014-11-15 | 2015-05-06 | 深圳市掌翼星通科技有限公司 | A kind of vehicle-carried sound-controlled voice Telephoning system |
| CN107895578A (en) * | 2017-11-15 | 2018-04-10 | 百度在线网络技术（北京）有限公司 | Voice interactive method and device |
| CN107978316A (en) * | 2017-11-15 | 2018-05-01 | 西安蜂语信息科技有限公司 | The method and device of control terminal |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111756935A (en) * | 2019-12-12 | 2020-10-09 | 北京沃东天骏信息技术有限公司 | Information processing method of intelligent system and intelligent system |
| CN111131632A (en) * | 2019-12-24 | 2020-05-08 | 贵阳朗玛信息技术股份有限公司 | Method and system for distributing express |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103888581B (en) | A kind of communication terminal and its method for recording call-information | |
| CN106161749B (en) | Malicious telephone identification method and device | |
| CN103561086A (en) | Method for presenting schedule prompting message, terminal device and cloud server | |
| CN106341313A (en) | Method and apparatus for obtaining billing information | |
| RU2009141623A (en) | METHOD AND SYSTEM FOR DELIVERY OF CONTENT TO THE USER OF THE PHONE DEVICE | |
| US20170064084A1 (en) | Method and Apparatus for Implementing Voice Mailbox | |
| CN105812550A (en) | Voice call anti-interference method, voice call anti-interference device and terminal | |
| CN105049627A (en) | Card generation method and device | |
| CN109726265A (en) | Assist information processing method, equipment and the computer readable storage medium of chat | |
| CN103249034A (en) | Method and device for acquiring contact information | |
| CN106713575A (en) | Method and system of recording contact information in cellphone call | |
| CN109979474A (en) | Speech ciphering equipment and its user speed modification method, device and storage medium | |
| CN109192207A (en) | Voice communication assembly, voice communication method and system, equipment, storage medium | |
| CN102694896B (en) | In order to store the method for communicating number, terminal and system | |
| CN107360313A (en) | For identifying anti-the swindle communication system and method for Stranger Calls | |
| CN113039758A (en) | Method and related device for automatically replying information | |
| CN110782341A (en) | Business collection method, device, equipment and medium | |
| CN107690038A (en) | Business phonetic navigation method and device | |
| CN111447327A (en) | Fraud telephone identification method, device, storage medium and terminal | |
| CN111028834B (en) | Voice message reminding method and device, server and voice message reminding equipment | |
| CN105407205A (en) | Data output method and data output apparatus | |
| CN203242061U (en) | Identify card recognition-based bank queuing system | |
| CN109151148A (en) | Recording method, device, terminal and the computer readable storage medium of dialog context | |
| KR101033870B1 (en) | Method and device for processing spam call | |
| CN108924330A (en) | Information processing method, device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190111 |
|
| RJ01 | Rejection of invention patent application after publication |